Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15853
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms related to various fields, including radiation therapy and laboratory research

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    453
    +0.11
    0.3%
    1667
    +0.07
    0.2%
    849
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    359
    +0.11
    0.02
    466
    +0.07
    0.02
    887
    +0.07
    0.02
    Negative Logits
     pymysql
    -0.66
     smtplib
    -0.64
     hashlib
    -0.64
     heapq
    -0.63
     pylab
    -0.62
     pymongo
    -0.57
    Denote
    -0.55
     functools
    -0.54
    Jeudi
    -0.52
     shutil
    -0.52
    POSITIVE LOGITS
     plak
    0.66
     kafe
    0.65
     alkoh
    0.64
     karton
    0.60
     keramik
    0.58
     pü
    0.57
     FBref
    0.56
     silikon
    0.55
     antik
    0.55
     kosme
    0.55
    Activations Density 0.058%

    No Known Activations